AI Dynamics

Global AI News Aggregator

About

AI System Passes Rigorous Jailbreak Testing After Red Teaming

We challenged jailbreakers to try to break a prototype version of the system to test its robustness. After thousands of hours of red teaming, not one participant found a reliable jailbreak that extracted detailed information across a set of 10 harmful questions.

→ View original post on X — @anthropicai